Gistology

making sense of the world

Sentiment Analysis

Sentiment Analysis has become, in recent years, an essential tool. One of the most important concepts in human thought is that of good versus bad, liking versus disliking. Sentiment Analysis processes a text and returns the detected sentiment, whether the writer has a positive, negative, or neutral opinion regarding the subject matter. Sentiment often indicates something of great value to business: Success versus failure; winning versus losing; demand versus lack of interest.

Sentiment Analysis remains a great challenge. In many applications, computer systems achieve a rate of correct classification that is far below perfection and in some cases, not much better than random responses. In fairness, people also fail to agree on sentiment of a given text, indicating the inherent difficulty. Still, it is clear that human readers are more accurate than computer systems in evaluating sentiment, except for computers' one great advantage: Speed. When a business has a large amount of text to evaluate in a short amount of time, it is often more useful to have all of the text classifed quickly than to have many people read all of it or a few people sample some of it. Sentiment Analysis is therefore increasingly an essential solution for Customer Relation Management and Social Media Monitoring. Sentiment Analysis is particularly powerful when it is paired with Keyword Extraction and Named Entity Recognition, to indicate what things a text is talking about, and what it has to say about those things.

Key to Gistology's philosophy is to provide the same value that Sentiment Analysis has proven to have in English for other languages, for companies that have interests in other markets, or for companies that have a global reach and want to find one provider to cover all of their needs.


Sentiment Analysis Keyword Extraction Named Entity Recognition Language Detection
English German Spanish French Italian Portuguese Russian Arabic Chinese Japanese Dutch Swedish Norwegian Danish